What is backrest-mcp AGENTS.md?

A set of AGENTS.md instructions for a Python server that connects coding agents to the Backrest backup manager. It documents the server's structure, setup, and available backup tools.

Querying backup health, configuration, snapshots, files, summaries, operations, and logs; starting backups or maintenance; and, with explicit permission, forgetting snapshots or restoring data to staging paths.

It gives an agent the project context needed to work with Backrest without repeatedly inspecting the codebase. It also distinguishes read-only actions from actions that can remove snapshots or restore data.

How TadMSTR/backrest-mcp configures Codex and OpenCode

Reuse

Borrowing it

Nothing to install: this file belongs to TadMSTR/backrest-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/TadMSTR/backrest-mcp/main/AGENTS.md

Clone the repo

git clone --depth 1 https://github.com/TadMSTR/backrest-mcp

Made for: Codex, OpenCode.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/tadmstr/backrest-mcp/agents-md/github.svg)](https://agentmods.dev/instructions/tadmstr/backrest-mcp/agents-md)

Your own site

<a href="https://agentmods.dev/instructions/tadmstr/backrest-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/tadmstr/backrest-mcp/agents-md/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/tadmstr/backrest-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/tadmstr/backrest-mcp/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 2,392 This file is loaded in full into every session.

When invoked 2,392 The same file — it is already loaded in full.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

Model	Per session	Once invoked
Fable 5.1	$0.02392	$0.02392
Opus 5.5	$0.00957	$0.00957
Sonnet 5.5	$0.00478	$0.00478
Haiku 4.5	$0.00239	$0.00239

Measured 19d ago against content hash c8b48db4def3, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

backrest-mcp AGENTS.md scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 19d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

AGENTS.md · 162 lines

How it starts

The opening of the file, as written. The whole thing — 162 lines — stays where its author put it; the contents beside it link to each section on GitHub.

backrest-mcp

Python/FastMCP MCP server (stdio or loopback HTTP transport) wrapping the Backrest backup manager REST API. Field names target the deployed Backrest v1.13.0 connect-rpc API (upstream main has since diverged — see CHANGELOG.md 0.3.0).

What it does

Provides MCP tools for querying backup operations, listing snapshots, reading config, browsing snapshot contents, triggering backups, running repo maintenance tasks, and (with explicit opt-in) forgetting snapshots and restoring data to staging paths.

Tools

Always registered (read-only):

get_health() — Reachability + credential health (ok/auth_failed/unreachable); poll-safe
get_config() — Secret-free allowlist projection of the Backrest config (redact.py); never returns repo passwords, env values, flags, hook targets or the multihost block
list_plans() — Projected plans (paths, excludes, repo, schedule, retention); prefer to get_config for coverage questions
find_plan_for_path(path) — Plans covering an absolute path, with the first matching exclude; approximate restic matching, pure string ops
get_backup_freshness(max_age_hours?) — Per plan: last SUCCESS/WARNING backup, age, latest status, ok/stale/unscheduled; returns stale_count and unscheduled_count (a disabled schedule is never stale, so monitor both)
list_snapshots(repo_id?, plan_id?) — List snapshots; no args → enumerate all repos, tag each
list_snapshot_files(repo_id, snapshot_id, path?) — Browse files (repo_id resolved to GUID internally)
get_summary() — 30-day dashboard stats per repo and plan
get_operations(plan_id?, repo_id?, limit?) — Recent operations with status icons + log refs
get_logs(ref, max_bytes?) — Read an operation's log (ref surfaced by get_operations; Connect stream)
get_download_url(operation_id, file_path) — Signed URL for a restored file

Registered when BACKREST_READONLY=false:

trigger_backup(plan_id, dry_run?) — Trigger a backup plan
do_repo_task(repo_id, task) — Run maintenance: index/prune/check/stats/unlock/forget
cancel_operation(operation_id) — Cancel a running operation

Read the full file on GitHub · 162 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

19d ago Changed · +37 lines · +732 tokens per session c8b48db4def3
2mo ago First seen · 125 lines · 1,660 tokens per session scan A 75d5ed3b4e27

Subscribe to this mod's changes

backrest-mcp AGENTS.md is an instructions file published in the GitHub repository TadMSTR/backrest-mcp (0 stars, last pushed 7d ago), licensed MIT. It adds 2,392 tokens to every session, about $0.0096 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

backrest mcp

backrest-mcp AGENTS.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
backrest-mcp AGENTS.mdTadMSTR/backrest-mcp	Instructions file	0	7d ago	MIT	A	2,392	Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	today	MIT	A	7,461	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	5,649	GitHub Copilot
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	today	MIT	A	4,680	Codex, OpenCode
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	3,093	GitHub Copilot
vscode model-prompts.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	2,022	GitHub Copilot

backrest-mcp: Instructions file for Codex